AI-Assisted Cardiotocography Interpretation for Early Detection of Fetal Distress: Implications for Obstetric Care in Saudi Arabia

References

[1] Aeberhard, J. L., Radan, A. P., Delgado-Gonzalo, R., Strahm, K. M., Sigurthorsdottir, H. B., Schneider, S., & Surbek, D. (2023). Artificial intelligence and machine learning in cardiotocography: A scoping review. European Journal of Obstetrics & Gynecology and Reproductive Biology, 281, 54–62.

[2] Ben M’Barek, I., Jauvion, G., & Ceccaldi, P. F. (2023). Computerized cardiotocography analysis during labor: A state-of-the-art review. Acta Obstetricia et Gynecologica Scandinavica, 102(2), 130–137.

[3] Francis, F., Luz, S., Wu, H., Stock, S. J., & Townsend, R. (2024). Machine learning on cardiotocography data to classify fetal outcomes: A scoping review. Computers in Biology and Medicine, 172, 108220.

[4] Mendis, L., Palaniswami, M., Brownfoot, F., & Keenan, E. (2023). Computerised cardiotocography analysis for the automated detection of fetal compromise during labour: A review. Bioengineering, 10(9), 1007.

[5] McCoy, J. A., Levine, L. D., Wan, G., Chivers, C., Teel, J., & La Cava, W. G. (2025). Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning. American Journal of Obstetrics and Gynecology, 232(1), 116.e1–116.e9.

[6] Ben M’Barek, I., Jauvion, G., Merrer, J., Koskas, M., Sibony, O., Ceccaldi, P. F., Le Pennec, E., & Stirnemann, J. (2025). DeepCTG 2.0: Development and validation of a deep learning model to detect neonatal acidemia from cardiotocography during labor. Computers in Biology and Medicine, 184, 109448.

[7] Ben M’Barek, I., Jauvion, G., Vitrou, J., Holmström, E., Koskas, M., & Ceccaldi, P. F. (2023). DeepCTG 1.0: An interpretable model to detect fetal hypoxia from cardiotocography data during labor and delivery. Frontiers in Pediatrics, 11, 1190441.

[8] Melaet, R., de Vries, I. R., Kok, R. D., Oei, S. G., Huijben, I. A. M., van Sloun, R. J. G., van Laar, J. O. E. H., & Vullings, R. (2024). Artificial intelligence based cardiotocogram assessment during labor. European Journal of Obstetrics & Gynecology and Reproductive Biology, 295, 75–85.

[9] Brown, J., et al. (2023). Clinical practice guidelines for intrapartum cardiotocography interpretation: A systematic review. Australian and New Zealand Journal of Obstetrics and Gynaecology.

[10] Zullo, F., Di Mascio, D., Raghuraman, N., Wagner, S., Brunelli, R., Giancotti, A., et al. (2023). Three-tiered fetal heart rate interpretation system and adverse neonatal and maternal outcomes: A systematic review and meta-analysis. American Journal of Obstetrics and Gynecology, 229(4), 377–387.

[11] NICE. (2022). Fetal Monitoring in Labour: NICE Guideline NG229. National Institute for Health and Care Excellence.

[12] Tsiligkeridou, S., Bolou, A., Xanthos, T., & Gourounti, K. (2023). Perinatal and neonatal outcomes using cardiotocography versus STAN and cardiotocography: A systematic review. Maedica, 18(4), 684–694.

[13] Pardasani, R., Vitullo, R., Harris, S., Yapici, H., & Beard, J. (2025). Development of a novel artificial intelligence algorithm for interpreting fetal heart rate and uterine activity data in cardiotocography.

[14] Saudi Vision 2030. (2024). Health Sector Transformation Report 2024. Kingdom of Saudi Arabia.

[15] Saudi Vision 2030. (2024). Vision 2030 Annual Report 2024. Kingdom of Saudi Arabia.

[16] Francis, F., Luz, S., Wu, H., Stock, S. J., & Townsend, R. (2024). Machine-learning approaches for fetal hypoxia detection and the challenges of clinical implementation. Computers in Biology and Medicine.

[17] Ben M’Barek, I., Jauvion, G., & Ceccaldi, P. F. (2023). Machine learning and deep learning applications in computerized intrapartum cardiotocography. Acta Obstetricia et Gynecologica Scandinavica.

[18] Mendis, L., Palaniswami, M., Brownfoot, F., & Keenan, E. (2023). Artificial intelligence approaches for automated fetal-compromise detection. Bioengineering.

[19] McCoy, J. A., et al. (2025). Deep-learning prediction of fetal acidemia using intrapartum electronic fetal monitoring. American Journal of Obstetrics and Gynecology.

[20] Aeberhard, J. L., et al. (2023). Artificial-intelligence-supported interpretation of fetal heart-rate monitoring. European Journal of Obstetrics & Gynecology and Reproductive Biology.

[21] Melaet, R., et al. (2024). Near-real-time AI assessment of fetal-heart-rate response during labour. European Journal of Obstetrics & Gynecology and Reproductive Biology.

[22] National Institute for Health and Care Excellence. (2023). Intrapartum Care: NICE Guideline NG235. NICE.

[23] Saudi Health Sector Transformation Program. (2024). Artificial Intelligence and Advanced Analytics in Healthcare Transformation. Kingdom of Saudi Arabia.

[24] Saudi Vision 2030. (2024). Digital Healthcare, Integrated Services and Preventive Health Transformation. Kingdom of Saudi Arabia.

[25] Ministry of Health, Kingdom of Saudi Arabia. (2024). Digital Health and Artificial Intelligence Initiatives in the Saudi Healthcare System.

@article{1722768,
      author = {Amina Majid},
      title = {AI-Assisted Cardiotocography Interpretation for Early Detection of Fetal Distress: Implications for Obstetric Care in Saudi Arabia},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {3},
      pages = {575-586},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722768.pdf},
      abstract = {Cardiotocography (CTG) remains one of the most frequently used methods for assessing fetal wellbeing during labor, particularly in pregnancies requiring continuous intrapartum surveillance. Despite its widespread use, conventional visual CTG interpretation is limited by interobserver and interobserver variability, inconsistent application of clinical guidelines, signal artefacts, and the relatively low positive predictive value of abnormal patterns for actual fetal hypoxia. Artificial intelligence (AI), machine learning (ML), and deep-learning techniques are increasingly being investigated as tools for improving the consistency and predictive value of CTG interpretation. This review evaluates contemporary evidence on AI-assisted CTG analysis for the early recognition of fetal compromise and examines its potential application within Saudi Arabian maternity services. A structured literature review was undertaken using evidence published primarily between 2020 and 2025. Current research demonstrates that machine-learning and deep-learning models can identify CTG abnormalities, predict fetal acidemia, and provide near-real-time assessment of fetal-heart-rate responses. Multicenter deep-learning studies have demonstrated promising discrimination for severe neonatal acidemia, while AI-based models may reduce subjectivity by continuously evaluating fetal-heart-rate and uterine-contraction patterns. However, clinical implementation remains limited by inconsistent outcome definitions, retrospective datasets, signal-quality problems, inadequate external validation, algorithmic bias, class imbalance, and limited explainability. AI should therefore augment rather than replace obstetric judgment. For Saudi Arabia, integrating AI-assisted CTG with electronic maternal records, central fetal-monitoring platforms, and structured escalation protocols could support high-volume maternity hospitals and align with the digital-health objectives of Saudi Vision 2030. A clinician-led human-AI model is proposed to strengthen fetal surveillance while maintaining patient safety, transparency, and professional accountability.},
      keywords = {Cardiotocography; Artificial Intelligence; Fetal Hypoxia; Fetal Distress; Fetal Monitoring; Machine Learning; Deep Learning; Clinical Decision Support; Saudi Arabia; Vision 2030.},
      month = {September},
      doi = {https://doi.org/10.64388/IREV10I3-1722768}
  }